Adaptive RBF neural-networks control for discrete nonlinear systems based on data

Abstract

In this paper, an adaptive radial basis function (RBF) neural-networks (NNs) control algorithm is developed for a class of nonlinear affine systems based on data from controller with constrained control inputs. First, a novel nonquadratic performance index functional is introduced to overcome the nonlinear control constraints, and then the iterative adaptive optimal control algorithm is developed to obtain the optimal feedback control of nonlinear systems. For facilitating the implementation of the iterative algorithm, RBF NNs are constructed to approximate the iterative performance index function and the control policy, respectively. Finally, we verify the effectiveness of adaptive control algorithm through experiments.